© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 4-RES-SM
    11. 9310
    Prev
    Next
    INDEX
    Explanations

    specific names and titles in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/4-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    410
    +0.13
    0.7%
    181
    +0.12
    0.7%
    280
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.13
    0.11
    181
    +0.12
    0.12
    369
    +0.11
    0.06
    Negative Logits
     itself
    -1.72
    ourced
    -1.57
    abouts
    -1.52
    tics
    -1.49
     branch
    -1.49
     choice
    -1.46
     exogenous
    -1.46
     entire
    -1.43
     instance
    -1.43
     countries
    -1.42
    POSITIVE LOGITS
    kowski
    2.35
    ovich
    2.12
    ikov
    2.03
    lander
    2.02
    berg
    2.01
    oux
    2.01
    elli
    1.99
    opoulos
    1.98
    lund
    1.96
    hoff
    1.94
    Activations Density 0.752%

    No Known Activations